This example shows how you might compose a richer financial research
agent using the Agents SDK. The pattern is similar to the `research_bot`
example, but with more specialized sub‑agents and a verification step.
The flow is:
1. **Planning**: A planner agent turns the end user’s request into a
list of search terms relevant to financial analysis – recent news,
earnings calls, corporate filings, industry commentary, etc.
2. **Search**: A search agent uses the built‑in `WebSearchTool` to
retrieve terse summaries for each search term. (You could also add
`FileSearchTool` if you have indexed PDFs or 10‑Ks.)
3. **Sub‑analysts**: Additional agents (e.g. a fundamentals analyst and
a risk analyst) are exposed as tools so the writer can call them inline
and incorporate their outputs.
4. **Writing**: A writer agent brings together the search snippets and
any sub‑analyst summaries into a long‑form markdown report plus a short
executive summary.
5. **Verification**: A final verifier agent audits the report for
obvious inconsistencies or missing sourcing.
## Context
By default, the outputs of tools are sent to the LLM again. The LLM gets
to read the outputs, and produce a new response. There are cases where
this is not desired:
1. Every tool results in another round trip, and sometimes the output of
the tool is enough.
2. If you force tool use (via model settings `tool_choice=required`),
then the agent will just infinite loop.
This enables you to have different behavior, e.g. use the first tool
output as the final output, or write a custom function to process tool
results and potentially produce an output.
## Test plan
Added new tests and ran existing tests
Also added examples.
Closes#117
`assert len(spans) == 12` is a very weak assertion. This PR asserts the
exported traces and spans more precisely in a readable tree format. And
when the format of an exported trace/span changes (e.g. a new key is
added to every span), you can use `pytest --inline-snapshot=fix` to
update all relevant tests automatically. See
https://15r10nk.github.io/inline-snapshot/latest/ for more info.
## Changes
- In this handoff example, we need to use `first_agent` with
`random_number_tool`, instead of `second_agent` without that tool, since
the user is asking to generate a random number.
- fixed typo in comments
# Summary
This adds the missing TracingProcessor export to __init__.py.
# Behavior
When trying to add a custom tracing processor, the TracingProcessor
importing fails with not found error when trying the example usage
proposed in issue #164
Specifically this line throws the error:
`add_trace_processor(MyTracingProcessor("output"))`
# Expected Behavior
Inspecting the init file, simply the import/export was missing. Adding
these made the example code work for me
# Test plan
Local dev of example code in #164
# Issue number
#164
# Checks
None
These classes print a really long, unreadable output by default. This
trims it to the main useful info (i.e. output, last agent, overview of
run).
---
[//]: # (BEGIN SAPLING FOOTER)
* __->__ #196
* #195
Rohan Mehta
Dominik Kundel
Shyamal H Anadkat
James Hills
jhills20
Vincent Koc
CCM
Dmitry Pimenov
B-Step62
Akshay Deo
Alex Hall
Carlos Souza